Automatic modulation classification (AMC) is becoming increasingly important for its fundamental role in dynamic spectrum access, which can support 5G wireless communications to refarm the spectrum resource with low utilization. In order to achieve a better classification performance, several AMC methods based on prototype and variant of convolutional neural networks (CNNs) have been proposed. However, most existing AMC methods based on CNNs only use monomodal information from either time domain or frequency domain. The complementary processing gain, which can be obatianed by fusing multimodal information from multiple transformation domain together, is neglected. To address the issue, we exploit a waveform-spectrum multimodal fusion (WSMF) method to realize AMC based on deep residual networks (Resnet). After extracting features from multimodal information using Resnet, we adopt a feature fusion strategy to merge multimodal features of signals to obtain more discriminating features. Simulation results demonstrate the superior performance of our proposed WSMF method compared with traditional CNNs based AMC method using single modality information. Our proposed method can distinguish among sixteen modulation signals, and it works well even for higher-order digital modulation types like 256QAM and 1024QAM.

The mobile and flexible unmanned aerial vehicle (UAV) with mobile edge computing (MEC) can effectively relieve the computing pressure of the massive data traffic in 5G Internet of Things. In this paper, we propose a novel online edge learning offloading (OELO) scheme for UAV-assisted MEC secure communications, which can improve the secure computation performance. Moreover, the problem of information security is further considered since the offloading information of terminal users (TUs) may be eavesdropped due to the light-of-sight characteristic of UAV transmission. In the OELO scheme, we maximize the secure computation efficiency by optimizing TUs' binary offloading decision and resource management while guaranteeing dynamic task data queue stability and minimum secure computing requirement. Since the optimization problem is fractionally structured, binary constrained and multi-variable coupled, we first utilize the Dinkelbach method to transform the fractionally structured problem into a tractable form. Then, OELO generates the offloading decision based on deep reinforcement learning (DRL) and optimizes the resource management in an iterative manner through successive convex approximation (SCA). Simulation results show that the proposed scheme achieves better computing performance and enhances the stability and security compared with benchmarks.

Direction-of-arrival (DOA) estimation is a vital research topic in array signal processing, with extensive applications in many fields. In recent years, deep learning has been applied to DOA estimation to improve the performance. However, most existing deep learning-based DOA estimation methods extract DOA information from the covariance matrix (CM) input. In this paper, we introduce a novel deep learning-based DOA estimation scheme that utilizes the raw in-phase (I) and quadrature (Q) components of the signal as the input. We formulate the problem as single-label classification and multi-label classification based on the number of signal sources. We design a convolutional neural network to solve the problems and to adapt to different number of snapshots. We also propose a deep learning regression-based method to overcome the limitations of classify-based methods in dealing with off-grid angles. We conduct extensive experiments with simulations and over-the-air collected signals to analyze the performance of the proposed method in various scenarios including different SNRs, additive generalized Gaussian noise (AGGN) and extreme multi-source DOA estimation. Results demonstrate that our proposed method outperforms the existing deep learning-based DOA estimation methods.

Deep learning methods achieve great success in many areas due to their powerful feature extraction capabilities and end-to-end training mechanism, and recently they are also introduced for radio signal modulation classification. In this paper, we propose a novel deep learning framework called SigNet, where a signal-to-matrix (S2M) operator is adopted to convert the original signal into a square matrix first and is co-trained with a follow-up CNN architecture for classification. This model is further accelerated by integrating 1D convolution operators, leading to the upgraded model SigNet2.0. The simulations on two signal datasets show that both SigNet and SigNet2.0 outperform a number of well-known baselines. More interestingly, our proposed models behave extremely well in small-sample learning when only a small training dataset is provided. They can achieve a relatively high accuracy even when 1% training data are kept, while other baseline models may lose their effectiveness much more quickly as the datasets get smaller. Such result suggests that SigNet/SigNet2.0 could be extremely useful in the situations where labeled signal data are difficult to obtain. The visualization of the output features of our models demonstrates that our model can well divide different modulation types of signals in the feature hyper-space.

A canonical wireless communication system consists of a transmitter and a receiver. The information bit stream is transmitted after coding, modulation, and pulse shaping. Due to the effects of radio frequency (RF) impairments, channel fading, noise and interference, the signal arriving at the receiver will be distorted. The receiver needs to recover the original information from the distorted signal. In this paper, we propose a new receiver model, namely DeepReceiver, that uses a deep neural network to replace the traditional receiver’s entire information recovery process. We design a one-dimensional convolution DenseNet (1D-Conv-DenseNet) structure, in which global pooling is used to improve the adaptability of the network to different input signal lengths. Multiple binary classifiers are used at the final classification layer to achieve multi-bit information stream recovery. We also exploit the DeepReceiver for unified blind reception of multiple modulation and coding schemes (MCSs) by including signal samples of corresponding MCSs in the training set. Simulation results show that the proposed DeepReceiver performs better than traditional step-by-step serial hard decision receiver in terms of bit error rate under the influence of various factors such as noise, RF impairments, multipath fading, cochannel interference, dynamic environment, and unified reception of multiple MCSs.

Our digital world is full of time series and graphs which capture the various aspects of many complex systems. Traditionally, there are respective methods in processing these two different types of data, e.g., Recurrent Neural Network (RNN) and Graph Neural Network (GNN), while in recent years, time series could be mapped to graphs by using the techniques such as Visibility Graph (VG), which simultaneously captures relevant aspects of both local and global dynamics in an easy way, so that researchers can use graph algorithms to mine the knowledge in time series and gain special latent graph representation features. Such mapping methods establish a bridge between time series and graphs, and have high potential to facilitate the analysis of various real-world time series. However, the VG method and its variants are just based on fixed rules and thus lack of flexibility, largely limiting their application in reality. In this paper, we propose an Adaptive Visibility Graph (AVG) algorithm that can adaptively map time series into graphs, based on which we further establish an end-to-end classification framework AvgNet, by utilizing GNN model DiffPool as the classifier. We then adopt AvgNet for radio signal modulation classification which is an important task in the field of wireless communication. The simulations validate that AvgNet outperforms a series of advanced deep learning methods, achieving the state-of-the-art performance in this task.